[OpenAI] Reinforcement Learning with Prediction-Based Rewards

Nov 1, 2018

quote

We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agents to explore their environments through curiosity, which for the first time[1]

There is an anonymous ICLR submission concurrent with our own work which exceeds human performance, though not to the same extent.

https://openai.com/blog/reinforcement-learning-with-prediction-based-rewards/

← Back to all articles         Quick Navigation:    Next:[ j ] – Prev:[ k ] – List:[ l ]